In seismic structural engineering, different methods are used to evaluate performance. Simplified approaches provide conservative estimates, while advanced analyses achieve higher precision at the cost of significant computational effort. Nonlinear Time History Analysis (NTHA) remains the most reliable method, but its high computational demand has led many researchers to propose simplified models, often resulting in conservative outcomes. This study proposes an Artificial Intelligence (AI)-based method to approximate NTHA. An Autoregressive Neural Network (ARNN) is developed to generate complete time-history responses of structures with minimal error relative to NTHA. Using ground motion data and the first three fundamental periods as inputs, the ARNN replicates NTHA responses with high accuracy. Unlike conventional surrogate models that predict only peak responses, the ARNN produces the entire response history. The ARNN is further integrated with a moment-based reliability framework employing the four-moment Pearson distribution (4M-Pearson), enabling efficient and accurate seismic reliability assessment. A three-story base-isolated steel structure is analyzed as a case study. Results demonstrate that the proposed ARNN achieves high precision in predicting both structural time-history responses and seismic reliability.

Recycled Aggregate Concrete (RAC) represents a significant innovation aimed at reducing the carbon footprint in the construction industry. Over the past few decades, numerous investigations and experiments have confirmed the viability of RAC as a construction material when the optimal combination of recycled and natural aggregates is used. This study seeks to further enhance the application of RAC by providing a robust framework for determining the optimal RAC mixture. To achieve this, machine learning is developed to predict the compressive strength of RAC by considering various mixture properties. To improve the accuracy of these predictions, the Symbiotic Organism Search (SOS) metaheuristic algorithm is employed, not only to fine-tune the machine learning hyperparameters but also to select the most suitable model. In this study, the SOS algorithm is tasked with choosing between Artificial Neural Networks (ANN), Support Vector Machines (SVM), or Random Forests (RF), based on predefined upper and lower bounds for their hyperparameters. The resulting machine learning model is then integrated with the novel Pareto Front Symbiotic Organism Search (PF-SOS) to generate a Pareto front of optimal mixtures, with compressive strength and production cost as the objectives. To validate the efficiency of the proposed method, the PF-SOS results are compared with those from other well-known multi-objective optimization algorithms. The findings demonstrate that PF-SOS offers faster convergence and a broader range of mixture options within the same function evaluation limit.

Sensitivity analysis is a decisive step in experimental and numerical structural mechanics. The analysis of structural model quantifies the importance of each input parameter, potential interaction and effects on structural response. Therefore, this study aimed to help reduce the uncertainty surrounding major variables, providing valuable guidance for conducting future experiments. During the investigation, numerically deterministic sensitivity analysis based on multicriteria model evaluations of load-displacement curves representing actual behavior of the member correctly, were reviewed. Multicriteria model combined the evaluation of peak load, energy dissipation before ultimate loading, and toughness of load-displacement response. The methodology led to a strong sensitivity analysis method, generating an agreement between numerical and experimental responses. Moreover, an investigation of the method was presented for a geopolymer haunch, the numerical model was based on rigid body spring model (RBSM), which enabled precise behavior simulation of reinforced concrete structures. RBSM was refined, enabling in-depth evaluation of stress-strain contours, plasticity index, initial crack formation and crack propagation, as well as RBSM-spring failure modes. The proposed multicriteria sensitivity analysis can be implemented with other simulation methods, such as finite element analysis (FEA) and structural simulation software. The recommended method is applicable to any structural member, where laboratory-tested full-scale specimens were functioning as validation tools. Following the proposed multicriteria sensitivity analysis, experimental load-displacement curves of this study supported the results of numerical RBSM in an acceptable range of error predictions.

Asphalt pavement consists of aggregates resulting in a waste material at end of its life. The aggregates can be reused as basic material for asphalt or cementitious binding agents. In both scenarios, the recycled aggregates should provide a good bond with the binder to achieve strength. This study focuses on reusing recycled asphalt aggregates (RAA) in mortar. The major weakness of RAA is the thin oily film originating from the asphalt residue, weakening the bond with cement. The pyrolysis method is accessed in an attempt to overcome this weakness. Three scenarios were investigated; the use of virgin aggregates (VA), RAA, and pyrolysis recycled asphalt aggregate (PRAA) as constituent in mortar. All variables were set a constant except for the aggregate type, the VA mortar function as controlling element. This research is methodologically based on experimental data conducted in the laboratory, while aggregate samples were taken from the field. To analyze the influence of pyrolysis to the aggregate-to-cement bond behaviour, qualitative and quantitative data were collected. The quantitative data were the mechanical properties, the mortar tensile, and compression strength. The qualitative data were obtained from scanning electron microscope readings to visually observe the aggregate surface roughness and voids, including the aggregates cross-section and pre-existing micro-cracks in the aggregate-to-cement interface. Supporting data were the aggregates‘ abrasion rate and absorption. The RAA resulted in a significant mortar strength decrease. This conclusion was supported by the findings of pre-existing cracks in the interfacial transition zone. The pyrolysis method improved the compression strength but negligibly affected the tensile behavior. The compression and tensile strength increased as a function of time for both RAA and PRAA, and a strength convergence was reached at 28 days. The PRAA is considered an option for reuse in mortar, supporting nature conservation.

In this paper, the elevated temperature on a concrete-galvalume composite beam's flexural strength based on the numerical and experimental methods is investigated. The strategy is to perform modeling and simulation of the flexural test based on finite element method (FEM) at room temperature and validate its results to experimental data at the same temperature. When the numerical model was proven valid, the model was utilized to simulate the effect of elevated temperatures on the composite element. The study concludes that the flexural strength of the beam decreases at higher temperature. Additionally, it was shown that cracking moments is susceptible to temperature fluctuation and the failure modes are sensitive concerning the elevated temperature.